Skills
Navigate
skills/googleworkspace/cli/gws-sheets/Gen Agent Trust Hub

gws-sheets

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a command-line tool named gws to interact with Google Sheets API resources. It provides instructions for executing methods like batchUpdate, create, and get via shell commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves reading and processing data from external spreadsheets. This creates a surface for indirect prompt injection, where content within a spreadsheet could contain malicious instructions intended to manipulate the agent's logic during processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 10:41 PM
Security Audit — agent-trust-hub — gws-sheets